Transactions on Data Analysis in Social Science2821-19361320190901A Review of Recommender System Algorithms in Social Networks and Their Challenges11712823356210.47176/TDASS.2019.117ENS.YeganehPh.D. Candidate, Department of Computer Engineering, Sanandaj Branch, Islamic Azad University, Sanandaj, IranS. A.Sheikh AhmadiDepartment of Computer Engineering, Sanandaj Branch, Islamic Azad University, Sanandaj, IranJournal Article20190216Today, the stock market has become a crucial channel for mobilizing investors’ capital. As a key indicator of a nation’s economic and financial activities, the stock exchange plays a pivotal role in reflecting the overall economic performance of a country or region. Predicting stock price movements remains one of the most challenging tasks in the financial domain. Accurate stock prediction not only enhances investors’ profitability but also contributes to national economic growth. Given the dynamic, complex, nonlinear, and nonparametric nature of stock markets, precise forecasting of stock price variations is essential for developing effective trading strategies. Researchers have employed various methodologies for stock market prediction, among which feature extraction and classification constitute the two fundamental processes. This study reviews and analyzes different feature extraction methods categorized into four types and classification techniques applied in prior research using artificial intelligence and mathematical models. The findings indicate that, due to the nonlinear nature of financial data, neural networks, particularly those employing hybrid or ensemble feature extraction approaches, demonstrate the highest efficiency and predictive performance in stock market forecasting.https://www.transoscience.ir/article_233562_23dce63f8a24174100bc21b8e0522da3.pdfTransactions on Data Analysis in Social Science2821-19361320190901Design, Implementation, and Effectiveness Evaluation of an Electronic Performance Support System on Teachers’ Attitudes and Performance in Instructional Design12913623356410.47176/TDASS.2019.129ENK.TaghipourAssistant Professor, Department of Educational Sciences, University of Tabriz, Tabriz, Iran0000-0001-6799-7720Journal Article20190309In recent years, with the emergence of electronic performance support systems (EPSS), the effectiveness of traditional and electronic internships for improving teachers’ instructional performance has been questioned. Accordingly, the present study aimed to examine the effectiveness of an EPSS on teachers’ attitudes toward the course and their performance in instructional design for science education. The study employed an experimental research method with a post-test control group design. The research population included physics education students admitted in 2013 at Shahid Sharafat Higher Education Center. Participants were randomly assigned to experimental and control groups. The effectiveness of the course was assessed through two variables: attitude and performance. Data collection instruments included an attitude assessment questionnaire and an instructional design performance checklist based on Merrill’s instructional model (teaching of concepts and laws at the application level). The content validity of all instruments was confirmed through expert review. The reliability of the attitude assessment questionnaire was calculated using Cronbach’s alpha coefficient (α = 0.87), and the reliability of the instructional design performance checklist for science education at the application level was confirmed through inter-rater reliability (r = 0.73). The collected data were analyzed using descriptive and inferential statistics, including multivariate analysis of variance (MANOVA) and independent samples t-test. The results revealed that teachers who benefited from the electronic performance support system demonstrated more positive attitudes toward the course and performed better in instructional design for science education based on Merrill’s instructional model compared to those who participated in electronic internships.https://www.transoscience.ir/article_233564_40dce387c7432515554e32105dfa84b0.pdfTransactions on Data Analysis in Social Science2821-19361320190901The Effect of Eight Weeks of High-Intensity Interval Training on C1q/TNF5 Serum Levels and Insulin Resistance in Obese Men13714223357010.47176/TDASS.2019.137ENM.KarimiAssistant Professor, Faculty of Faculty of Science, Qom University of Technology, Qom, Iran0000-0002-6388-622XJournal Article20190528C1q/TNF5 is a protein belonging to the C1q/TNF group, playing a role in glucose metabolism. The aim of this research was to investigate the effect of eight weeks of high-intensity interval training on C1q/TNF5 levels in obese men. In a semi-experimental study with a pre-test and post-test design, 24 obese men (BMI: 32.3 ± 1.1 kg/m², age: 34.7 ± 2.6 years) were purposefully selected. Participants were randomly divided into equal control and experimental groups. The experimental group underwent eight weeks of high-intensity interval training (three sessions per week). Blood samples were collected from both groups before and after the eight-week exercise intervention under fasting conditions. The data were analyzed using independent and paired t-tests (p < 0.05). After eight weeks of high-intensity interval training, a significant reduction was observed in serum levels of C1q/TNF5 (p = 0.001). Additionally, insulin resistance index significantly decreased (p = 0.004). Overall, it appears that eight weeks of high-intensity interval training can lead to improvements in insulin resistance and glucose metabolism in obese men.https://www.transoscience.ir/article_233570_89148838e27c7985877065bf2546f063.pdfTransactions on Data Analysis in Social Science2821-19361320190901Comparison of the Effect of a Period of Aquatic and Land-Based Exercises on Pain, Disability, and Muscle Endurance in Women with Non-specific Chronic Low Back Pain14315223357210.47176/TDASS.2019.143ENS.Alaei ParapariMSc in Sports Pathology and Corrective Movements, Department of Biomechanics and Sports Pathology, Faculty of Physical Education and Sport Sciences, Kharazmi University, Tehran, IranM.KhodaeiMSc in Sports Pathology and Corrective Movements, Department of Biomechanics and Sports Pathology, Faculty of Physical Education and Sport Sciences, Kharazmi University, Tehran, IranJournal Article20190213Background: Nonspecific chronic low back pain is one of the most prevalent musculoskeletal disorders. Aquatic and land-based exercises are commonly used by physiotherapists for the management and treatment of chronic low back pain. Pain, functional disability, and reduced muscle endurance are frequent complaints among these patients. Objective: The present study aimed to compare the effects of a course of aquatic and land-based exercises on pain, disability, and muscle endurance in women with nonspecific chronic low back pain. Methods: This quasi-experimental study employed a pretest-posttest design. Thirty women aged 20 to 45 years, selected via convenience sampling, were randomly assigned into three groups: a control group, which performed routine activities; a land-based exercise group, which performed structured exercises on the ground; and an aquatic exercise group, which performed exercises in water. The intervention lasted six weeks for both the land-based and aquatic exercise groups. Pain intensity, functional disability, and muscle endurance were assessed at pretest and posttest stages. Data were analyzed using repeated measures ANOVA, ANCOVA, independent t-tests, and paired t-tests. Results: Both aquatic and land-based exercises were effective in reducing pain, improving functional disability, and enhancing muscle endurance. Conclusion: The findings suggest that implementing aquatic or land-based exercise programs can be beneficial for women suffering from nonspecific chronic low back pain.https://www.transoscience.ir/article_233572_65329bf8a4b71512e57552cd2e7f1458.pdfTransactions on Data Analysis in Social Science2821-19361320190901Comparison of the Effect of 10 and 20 Grams of Creatine on GH, IGF-1 Levels in Professional Basketball Players after a Session of Intense Interval Training15316223357410.47176/TDASS.2019.153ENE.BarjisianDepartment of Exercise Physiology, Faculty of Physical Education and Sport Sciences, University of Tehran, Tehran, IranJournal Article20190521The present study aimed to compare the effects of 10 and 20 grams of creatine supplementation on growth hormone (GH) and insulin-like growth factor-1 (IGF-1) levels in professional basketball players following a single session of high-intensity interval training. For this purpose, 21 professional basketball players were selected through convenience sampling and randomly assigned to three groups of seven participants each: 10-gram creatine loading, 20-gram creatine loading, and a placebo control group. Blood sampling was conducted at three stages: before the initiation of creatine or placebo supplementation; 24 hours after six days of creatine loading; and 24 hours after performing the high-intensity interval training session. Data were analyzed using repeated-measures analysis of variance (ANOVA). The results indicated that supplementation with either 10 or 20 grams of creatine had no significant effect on GH or IGF-1 levels in professional basketball players. However, high-intensity interval training had a significant effect on the levels of GH and IGF-1, leading to a marked increase in both hormones.https://www.transoscience.ir/article_233574_8eef5ee2bd43c720798c7b4dd45a8b24.pdfTransactions on Data Analysis in Social Science2821-19361320190901Feature Extraction and Classification Methods for Stock Market Trend Prediction16317023356110.47176/TDASS.2019.163ENG.RanjbaranDepartment of Computer Engineering, Faculty of Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, IranM.S.MoinAssociate Professor, Information Technology Research Institute, Research Institute for ICT (ITRC), Tehran, IranJournal Article20190204Today, the stock market has become a crucial channel for mobilizing investors’ capital. As a key indicator of a nation’s economic and financial activities, the stock exchange plays a pivotal role in reflecting the overall economic performance of a country or region. Predicting stock price movements remains one of the most challenging tasks in the financial domain. Accurate stock prediction not only enhances investors’ profitability but also contributes to national economic growth. Given the dynamic, complex, nonlinear, and nonparametric nature of stock markets, precise forecasting of stock price variations is essential for developing effective trading strategies. Researchers have employed various methodologies for stock market prediction, among which feature extraction and classification constitute the two fundamental processes. This study reviews and analyzes different feature extraction methods categorized into four types and classification techniques applied in prior research using artificial intelligence and mathematical models. The findings indicate that, due to the nonlinear nature of financial data, neural networks, particularly those employing hybrid or ensemble feature extraction approaches, demonstrate the highest efficiency and predictive performance in stock market forecasting.https://www.transoscience.ir/article_233561_53bc77b31096cecd8d2400859d034b69.pdf